deliverable/linux.git
8 years agoMerge branches 'doc.2016.04.19a', 'exp.2016.03.31d', 'fixes.2016.03.31d' and 'torture...
Paul E. McKenney [Thu, 21 Apr 2016 20:48:20 +0000 (13:48 -0700)] 
Merge branches 'doc.2016.04.19a', 'exp.2016.03.31d', 'fixes.2016.03.31d' and 'torture.2016.04.21a' into HEAD

doc.2016.04.19a: Documentation updates
exp.2016.03.31d: Expedited grace-period updates
fixes.2016.03.31d: Miscellaneous fixes
torture.2016.004.21a Torture-test updates

8 years agorcutorture: Add boot-time adjustment of leaf fanout
Paul E. McKenney [Wed, 30 Mar 2016 21:16:22 +0000 (14:16 -0700)] 
rcutorture: Add boot-time adjustment of leaf fanout

Currently, the rcutorture scripts do not test boot-time adjustment of
leaf fanout (via the rcutree.rcu_fanout_leaf boot parameter), as was noted
during testing carried out by Iftekhar Ahmed of Oregon State University.
This commit therefore adjusts TREE04's CONFIG_RCU_FANOUT_LEAF from 4 to 3,
and also adds rcutree.rcu_fanout_leaf=4 to its boot parameters.  This
change forces RCU's boot-time geometry-change code to be exercised.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Add irqs-disabled test for call_rcu()
Paul E. McKenney [Wed, 30 Mar 2016 18:40:44 +0000 (11:40 -0700)] 
rcutorture: Add irqs-disabled test for call_rcu()

Mutation testing carried out by Iftekhar Ahmed of Oregon State
University showed that rcutorture is failing to test invocations
of call_rcu() having interrupts disabled.  This commit therefore
adds interrupt disabling around one of the existing invocations
of call_rcu() (and friends).

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Dump trace buffer upon shutdown
Paul E. McKenney [Wed, 30 Mar 2016 18:20:48 +0000 (11:20 -0700)] 
rcutorture: Dump trace buffer upon shutdown

When running from the scripts, rcutorture is completely headless,
so there is no way to to manually dump the trace buffer.  This commit
therefore unconditionally dumps the trace buffer upon timed shutdown.
However, if you are using rmmod to end the test, it is still up to you
to manually dump the trace buffer.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Don't rebuild identical kernel
Paul E. McKenney [Wed, 30 Mar 2016 17:48:06 +0000 (10:48 -0700)] 
rcutorture: Don't rebuild identical kernel

Currently, if the user specifies multiple runs of a given test
configuration, the scripting does multiple kernel builds.  This wastes
both time and disk space, so this commit makes the scripting use the
first build for all runs of a given test configuration.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Add OS-jitter capability
Paul E. McKenney [Tue, 29 Mar 2016 21:22:26 +0000 (14:22 -0700)] 
rcutorture: Add OS-jitter capability

This commit adds a --jitter OS-jitter capability to expose bugs based
on no-delay assumptions.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Add documentation for RCU's major data structures
Paul E. McKenney [Fri, 29 Jan 2016 00:49:24 +0000 (16:49 -0800)] 
documentation: Add documentation for RCU's major data structures

This commit adds documentation for RCU's major data structures,
including rcu_state, rcu_node, rcu_data, rcu_dynticks, and rcu_head.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Convert test duration to seconds early
Paul E. McKenney [Tue, 29 Mar 2016 17:50:38 +0000 (10:50 -0700)] 
rcutorture: Convert test duration to seconds early

This commit converts test duration from minutes to seconds early on
in order to prepare for upcoming OS-jitter-injection changes.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agotorture: Kill qemu, not parent process
Paul E. McKenney [Mon, 28 Mar 2016 21:44:42 +0000 (14:44 -0700)] 
torture: Kill qemu, not parent process

The current hang-check machinery in the rcutorture scripts uses "$!" of
a parenthesized bash statement to capture the pid.  Unfortunately, this
captures not qemu's pid, but rather that of its parent that implements
the parenthesized statement.  This commit therefore adjusts things so as
to capture qemu's actual pid, which then allows the script to actually
kill qemu in event of a kernel hang.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agotorture: Clarify refusal to run more than one torture test
Paul E. McKenney [Mon, 21 Mar 2016 22:36:40 +0000 (15:36 -0700)] 
torture: Clarify refusal to run more than one torture test

This commit clarifies error messages -- you only get to run one torture
test at a time!

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Consider FROZEN hotplug notifier transitions
Anna-Maria Gleixner [Thu, 17 Mar 2016 10:14:35 +0000 (11:14 +0100)] 
rcutorture: Consider FROZEN hotplug notifier transitions

The hotplug notifier rcutorture_cpu_notify() doesn't consider the
corresponding CPU_XXX_FROZEN transitions. They occur on
suspend/resume and are usually handled the same way as the
corresponding non frozen transitions.

Mask the switch case action argument with '~CPU_TASKS_FROZEN' to map
CPU_XXX_FROZEN hotplug transitions on corresponding non-frozen
transitions.

Cc: Josh Triplett <josh@joshtriplett.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Remove redundant initialization to zero
Paul E. McKenney [Tue, 1 Mar 2016 16:52:19 +0000 (08:52 -0800)] 
rcutorture: Remove redundant initialization to zero

The current code initializes the global per-CPU variables
rcu_torture_count and rcu_torture_batch to zero.  However, C does this
initialization by default, and explicit initialization of per-CPU
variables now needs a different syntax if "make tags" is to work.
This commit therefore removes the initialization.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcuperf: Do not wake up shutdown wait queue if "shutdown" is false.
Artem Savkov [Sun, 7 Feb 2016 12:31:39 +0000 (13:31 +0100)] 
rcuperf: Do not wake up shutdown wait queue if "shutdown" is false.

After finishing its tests rcuperf tries to wake up shutdown_wq even if
"shutdown" param is set to false, resulting in a wake_up() call on an
unitialized wait_queue_head_t which leads to "BUG: spinlock bad magic" and
"BUG: unable to handle kernel NULL pointer dereference".

Fix by checking "shutdown" param before waking up the queue.

Signed-off-by: Artem Savkov <artem.savkov@gmail.com>
8 years agorcutorture: Add largish-system rcuperf scenario
Paul E. McKenney [Tue, 2 Feb 2016 00:39:38 +0000 (16:39 -0800)] 
rcutorture: Add largish-system rcuperf scenario

This commit adds an rcuperf scenario named TREE54 that uses 54 CPUs and
provides a four-level rcu_node combining tree.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Avoid RCU CPU stall warning and RT throttling
Paul E. McKenney [Sun, 31 Jan 2016 05:32:09 +0000 (21:32 -0800)] 
rcutorture: Avoid RCU CPU stall warning and RT throttling

Running rcuperf can result in RCU CPU stall warnings and RT throttling.
These occur because on of the real-time writer processes does
ftrace_dump() while still running at real-time priority.  This commit
therefore prevents these problems by setting the writer thread back to
SCHED_NORMAL (AKA SCHED_OTHER) before doing ftrace_dump().

In addition, this commit adds a small fixed delay before dumping ftrace
buffer in order to decrease the probability that this dumping will
interfere with other writers' grace periods.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Add rcuperf holdoff boot parameter to reduce interference
Paul E. McKenney [Sun, 31 Jan 2016 04:56:38 +0000 (20:56 -0800)] 
rcutorture: Add rcuperf holdoff boot parameter to reduce interference

Boot-time activity can legitimately grab CPUs for extended time periods,
so the commit adds a boot parameter to delay the start of the performance
test until boot has completed.  Defaults to 10 seconds.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Make scripts analyze rcuperf trace data, if present
Paul E. McKenney [Sun, 31 Jan 2016 00:51:36 +0000 (16:51 -0800)] 
rcutorture: Make scripts analyze rcuperf trace data, if present

The rcuperf event-trace data is more accurate than are the rcuperf
printk()s because locking keeps things ordered.  This commit therefore
parses and analyzes this event-trace data if present, and falls back on
the printk()s otherwise.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Make rcuperf collect expedited event-trace data
Paul E. McKenney [Fri, 29 Jan 2016 22:58:17 +0000 (14:58 -0800)] 
rcutorture: Make rcuperf collect expedited event-trace data

This commit enables ftrace in the rcuperf TREE kernel build and adds
an ftrace_dump() at the end of rcuperf processing.  This data will be
used to measure the actual durations of the expedited grace periods
without the added delays inherent in the kernel-module measurements.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Print measure of batching efficiency
Paul E. McKenney [Wed, 13 Jan 2016 01:26:35 +0000 (17:26 -0800)] 
rcutorture: Print measure of batching efficiency

This commit adds a line giving the number of grace periods, the number
of batches, and the ratio.  The larger the ratio, the greater the
batching efficiency.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Set rcuperf writer kthreads to real-time priority
Paul E. McKenney [Tue, 12 Jan 2016 23:17:21 +0000 (15:17 -0800)] 
rcutorture: Set rcuperf writer kthreads to real-time priority

This commit forces more deterministic update-side behavior by setting
rcuperf's rcu_perf_writer() kthreads to real-time priority.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Bind rcuperf reader/writer kthreads to CPUs
Paul E. McKenney [Tue, 12 Jan 2016 22:15:40 +0000 (14:15 -0800)] 
rcutorture: Bind rcuperf reader/writer kthreads to CPUs

This commit forces more deterministic behavior by binding rcuperf's
rcu_perf_reader() and rcu_perf_writer() kthreads to their respective
CPUs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Documentation for rcuperf kernel parameters
Paul E. McKenney [Fri, 1 Jan 2016 21:47:19 +0000 (13:47 -0800)] 
rcutorture: Documentation for rcuperf kernel parameters

This commit adds documentation for the new rcuperf module's kernel
boot parameters.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Add RCU grace-period performance tests
Paul E. McKenney [Fri, 1 Jan 2016 02:33:22 +0000 (18:33 -0800)] 
rcutorture: Add RCU grace-period performance tests

This commit adds a new rcuperf module that carries out simple performance
tests of RCU grace periods.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Expedited-GP batch progress access to torturing
Paul E. McKenney [Tue, 12 Jan 2016 21:43:30 +0000 (13:43 -0800)] 
rcutorture: Expedited-GP batch progress access to torturing

This commit provides rcu_exp_batches_completed() and
rcu_exp_batches_completed_sched() functions to allow torture-test modules
to check how many expedited grace period batches have completed.
These are analogous to the existing rcu_batches_completed(),
rcu_batches_completed_bh(), and rcu_batches_completed_sched() functions.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Allow for rcupdate.rcu_normal
Paul E. McKenney [Fri, 1 Jan 2016 02:11:47 +0000 (18:11 -0800)] 
rcutorture: Allow for rcupdate.rcu_normal

Currently, rcu_torture_writer() checks only for rcu_gp_is_expedited()
when deciding whether or not to do dynamic control of RCU expediting.
This means that if rcupdate.rcu_normal is specified, rcu_torture_writer()
will attempt to dynamically control RCU expediting, but will nonetheless
only test normal RCU grace periods.  This commit therefore adds a check
for !rcu_gp_is_normal(), and prints a message and desists from testing
dynamic control of RCU expediting when doing so is futile.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcutorture: Update scripting to accommodate rcuperf
Paul E. McKenney [Mon, 11 Jan 2016 21:13:12 +0000 (13:13 -0800)] 
rcutorture: Update scripting to accommodate rcuperf

This commit adds the scripting changes to add support for the shiny
new rcuperf kernel module.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Dump ftrace buffer when kicking grace-period kthread
Paul E. McKenney [Wed, 17 Feb 2016 19:54:28 +0000 (11:54 -0800)] 
rcu: Dump ftrace buffer when kicking grace-period kthread

If it is necessary to kick the grace-period kthread, that is a good
time to dump the trace buffer in order to learn why kicking was needed.
This commit therefore does the dump.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Remove superfluous versions of rcu_read_lock_sched_held()
Boqun Feng [Wed, 23 Mar 2016 15:11:48 +0000 (23:11 +0800)] 
rcu: Remove superfluous versions of rcu_read_lock_sched_held()

Currently, we have four versions of rcu_read_lock_sched_held(), depending
on the combined choices on PREEMPT_COUNT and DEBUG_LOCK_ALLOC.  However,
there is an existing function preemptible() that already distinguishes
between the PREEMPT_COUNT=y and PREEMPT_COUNT=n cases, and allows these
four implementations to be consolidated down to two.

This commit therefore uses preemptible() to achieve this consolidation.

Note that there could be a small performance regression in the case
of CONFIG_DEBUG_LOCK_ALLOC=y && PREEMPT_COUNT=n.  However, given the
overhead associated with CONFIG_DEBUG_LOCK_ALLOC=y, this should be
down in the noise.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Awaken grace-period kthread if too long since FQS
Paul E. McKenney [Mon, 4 Jan 2016 04:29:57 +0000 (20:29 -0800)] 
rcu: Awaken grace-period kthread if too long since FQS

Recent kernels can fail to awaken the grace-period kthread for
quiescent-state forcing.  This commit is a crude hack that does
a wakeup if a scheduling-clock interrupt sees that it has been
too long since force-quiescent-state (FQS) processing.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Make FQS schedule advance only if FQS happened
Paul E. McKenney [Mon, 4 Jan 2016 00:42:18 +0000 (16:42 -0800)] 
rcu: Make FQS schedule advance only if FQS happened

Currently, the force-quiescent-state (FQS) code in rcu_gp_kthread() can
advance the next FQS even if one was not executed last time.  This can
happen due timeout-duration uncertainty.  This commit therefore avoids
advancing the FQS schedule unless an FQS was just executed.  In the
corner case where an FQS was not executed, but is due now, the code does
a one-jiffy wait.

This change prepares for kthread kicking.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Awaken grace-period kthread when stalled
Paul E. McKenney [Thu, 31 Dec 2015 16:48:36 +0000 (08:48 -0800)] 
rcu: Awaken grace-period kthread when stalled

Recent kernels can fail to awaken the grace-period kthread for
quiescent-state forcing.  This commit is a crude hack that does
a wakeup any time a stall is detected.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Overlap wakeups with next expedited grace period
Paul E. McKenney [Wed, 16 Mar 2016 23:47:55 +0000 (16:47 -0700)] 
rcu: Overlap wakeups with next expedited grace period

The current expedited grace-period implementation makes subsequent grace
periods wait on wakeups for the prior grace period.  This does not fit
the dictionary definition of "expedited", so this commit allows these two
phases to overlap.  Doing this requires four waitqueues rather than two
because tasks can now be waiting on the previous, current, and next grace
periods.  The fourth waitqueue makes the bit masking work out nicely.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Consolidate expedited GP code into exp_funnel_lock()
Paul E. McKenney [Wed, 16 Mar 2016 23:32:24 +0000 (16:32 -0700)] 
rcu: Consolidate expedited GP code into exp_funnel_lock()

This commit pulls the grace-period-start counter adjustment and tracing
from synchronize_rcu_expedited() and synchronize_sched_expedited()
into exp_funnel_lock(), thus eliminating some code duplication.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Consolidate expedited GP tracing into rcu_exp_gp_seq_snap()
Paul E. McKenney [Wed, 16 Mar 2016 23:27:44 +0000 (16:27 -0700)] 
rcu: Consolidate expedited GP tracing into rcu_exp_gp_seq_snap()

This commit moves some duplicate code from synchronize_rcu_expedited()
and synchronize_sched_expedited() into rcu_exp_gp_seq_snap().  This
doesn't save lines of code, but does eliminate a "tell me twice" issue.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Consolidate expedited GP code into rcu_exp_wait_wake()
Paul E. McKenney [Wed, 16 Mar 2016 23:22:25 +0000 (16:22 -0700)] 
rcu: Consolidate expedited GP code into rcu_exp_wait_wake()

Currently, synchronize_rcu_expedited() and rcu_sched_expedited() have
significant duplicate code.  This commit therefore consolidates some of
this code into rcu_exp_wake(), which is now renamed to rcu_exp_wait_wake()
in recognition of its added responsibilities.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Add exp_funnel_lock() fastpath
Paul E. McKenney [Wed, 16 Mar 2016 20:22:53 +0000 (13:22 -0700)] 
rcu: Add exp_funnel_lock() fastpath

This commit speeds up the low-contention case, especially for systems
with large rcu_node trees, by attempting to directly acquire the
->exp_mutex.  This fastpath checks the leaves and root first in
order to avoid excessive memory contention on the mutex itself.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Enforce expedited-GP fairness via funnel wait queue
Paul E. McKenney [Sun, 31 Jan 2016 01:57:35 +0000 (17:57 -0800)] 
rcu: Enforce expedited-GP fairness via funnel wait queue

The current mutex-based funnel-locking approach used by expedited grace
periods is subject to severe unfairness.  The problem arises when a
few tasks, making a path from leaves to root, all wake up before other
tasks do.  A new task can then follow this path all the way to the root,
which needlessly delays tasks whose grace period is done, but who do
not happen to acquire the lock quickly enough.

This commit avoids this problem by maintaining per-rcu_node wait queues,
along with a per-rcu_node counter that tracks the latest grace period
sought by an earlier task to visit this node.  If that grace period
would satisfy the current task, instead of proceeding up the tree,
it waits on the current rcu_node structure using a pair of wait queues
provided for that purpose.  This decouples awakening of old tasks from
the arrival of new tasks.

If the wakeups prove to be a bottleneck, additional kthreads can be
brought to bear for that purpose.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Shorten expedited_workdone* to exp_workdone*
Paul E. McKenney [Tue, 8 Mar 2016 22:43:44 +0000 (14:43 -0800)] 
rcu: Shorten expedited_workdone* to exp_workdone*

Just a name change to save a few lines and a bit of typing.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Force boolean subscript for expedited stall warnings
Paul E. McKenney [Tue, 12 Jan 2016 00:29:29 +0000 (16:29 -0800)] 
rcu: Force boolean subscript for expedited stall warnings

The cpu_online() function can return values other than 0 and 1, which
can result in subscript overflow when applied to a two-element array.
This commit allows for this behavior by using "!!" on the return value
from cpu_online() when used as a subscript.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Remove expedited GP funnel-lock bypass
Paul E. McKenney [Sun, 31 Jan 2016 01:23:19 +0000 (17:23 -0800)] 
rcu: Remove expedited GP funnel-lock bypass

Commit #cdacbe1f91264 ("rcu: Add fastpath bypassing funnel locking")
turns out to be a pessimization at high load because it forces a tree
full of tasks to wait for an expedited grace period that they probably
do not need.  This commit therefore removes this optimization.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Add expedited-grace-period event tracing
Paul E. McKenney [Fri, 29 Jan 2016 04:49:49 +0000 (20:49 -0800)] 
rcu: Add expedited-grace-period event tracing

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Add funnel-locking tracing for expedited grace periods
Paul E. McKenney [Fri, 29 Jan 2016 04:30:06 +0000 (20:30 -0800)] 
rcu: Add funnel-locking tracing for expedited grace periods

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Add event tracing definitions for expedited grace periods
Paul E. McKenney [Fri, 29 Jan 2016 04:25:09 +0000 (20:25 -0800)] 
rcu: Add event tracing definitions for expedited grace periods

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Fix synchronize_rcu_expedited() header comment
Paul E. McKenney [Fri, 29 Jan 2016 02:48:37 +0000 (18:48 -0800)] 
rcu: Fix synchronize_rcu_expedited() header comment

This commit brings the synchronize_rcu_expedited() function's header
comment into line with the new implementation.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Make cond_resched_rcu_qs() supply RCU-sched expedited QS
Paul E. McKenney [Wed, 13 Jan 2016 21:57:54 +0000 (13:57 -0800)] 
rcu: Make cond_resched_rcu_qs() supply RCU-sched expedited QS

Although cond_resched_rcu_qs() supplies quiescent states to all flavors
of normal RCU grace periods, it does nothing for expedited RCU-sched
grace periods.  This commit therefore adds a check for a need for a
quiescent state from the current CPU by an expedited RCU-sched grace
period, and invokes rcu_sched_qs() to supply that quiescent state if so.

Note that the check is racy in that we might be migrated to some other
CPU just after checking the per-CPU variable.  This is OK because the
act of migration will do a context switch, which will supply the needed
quiescent state.  The only downside is that we might do an unnecessary
call to rcu_sched_qs(), but the probability is low and the overhead
is small.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Make expedited RCU-preempt stall warnings count accurately
Paul E. McKenney [Wed, 13 Jan 2016 18:52:35 +0000 (10:52 -0800)] 
rcu: Make expedited RCU-preempt stall warnings count accurately

Currently, synchronize_sched_expedited_wait() simply sets the ndetected
variable to the rcu_print_task_exp_stall() return value.  This means
that if the last rcu_node structure has no stalled tasks, record of
any stalled tasks in previous rcu_node structures is lost, which can
in turn result in failure to dump out the blocking rcu_node structures.
Or could, had the test been correct.

This commit therefore adds the return value of rcu_print_task_exp_stall()
to ndetected and corrects the later test for ndetected.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Make expedited RCU-sched grace period immediately detect idle
Paul E. McKenney [Tue, 12 Jan 2016 16:33:37 +0000 (08:33 -0800)] 
rcu: Make expedited RCU-sched grace period immediately detect idle

Currently, sync_sched_exp_handler() will force a reschedule unless
this CPU has already checked in or unless a reschedule has already
been called for.  This is clearly wasteful if sync_sched_exp_handler()
interrupted an idle CPU, so this commit immediately reports the
quiescent state in that case.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Emphasize the call_rcu() is illegal from idle
Paul E. McKenney [Thu, 31 Mar 2016 18:00:08 +0000 (11:00 -0700)] 
documentation: Emphasize the call_rcu() is illegal from idle

Although call_rcu()'s fastpath works just fine on an idle CPU,
some branches of the slowpath invoke the scheduler, which uses
RCU.  Therefore, this commit emphasizes the fact that call_rcu()
must not be invoked from an idle CPU.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Sharpen up the no-readers quick quiz
Paul E. McKenney [Tue, 15 Mar 2016 20:40:28 +0000 (13:40 -0700)] 
documentation: Sharpen up the no-readers quick quiz

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Get rid of duplicate .htmlx file
Paul E. McKenney [Tue, 15 Mar 2016 20:25:20 +0000 (13:25 -0700)] 
documentation: Get rid of duplicate .htmlx file

This commit uses colors to obscure the quick-quiz answers, thus getting
rid of the .htmlx file.  Use your mouse to select the answer in order
to see the text.  Alternatively, use your favorite scripting language
to remove all occurences of "<font color="ffffff">" from the file.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Remove unnecessary images from requirements
Paul E. McKenney [Tue, 15 Mar 2016 18:03:36 +0000 (11:03 -0700)] 
documentation: Remove unnecessary images from requirements

This commit removes a cutesy cartoon and also a diagram that can
just as easily be represented by text.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Document illegality of call_rcu() from offline CPUs
Paul E. McKenney [Tue, 16 Feb 2016 00:52:35 +0000 (16:52 -0800)] 
documentation: Document illegality of call_rcu() from offline CPUs

There is already a blanket statement about no member of RCU's API
being legal from an offline CPU, but add an explicit note where it
states that it is illegal to invoke call_rcu() from an NMI handler.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Explain why rcu_read_lock() needs no barrier()
Paul E. McKenney [Tue, 16 Feb 2016 01:29:47 +0000 (17:29 -0800)] 
documentation: Explain why rcu_read_lock() needs no barrier()

This commit adds a Quick Quiz whose answer explains why the compiler
code reordering enabled by CONFIG_PREEMPT=n's empty rcu_read_lock()
and rcu_read_unlock() functions does not hinder RCU's ability to figure
out which RCU read-side critical sections have completed and not.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Add synchronize_rcu_mult() to the requirements
Paul E. McKenney [Thu, 7 Jan 2016 17:12:43 +0000 (09:12 -0800)] 
documentation: Add synchronize_rcu_mult() to the requirements

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Add real-time requirements from CPU-bound workloads
Paul E. McKenney [Sat, 12 Dec 2015 00:18:22 +0000 (16:18 -0800)] 
documentation:  Add real-time requirements from CPU-bound workloads

This commit records RCU's responsibility to avoid degrading latencies
of CPUs running tight loops within properly configured workloads,
both in kernel and in userspace.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agodocumentation: Make sample code and documentation consistent
Yao Dongdong [Mon, 7 Mar 2016 08:02:14 +0000 (16:02 +0800)] 
documentation: Make sample code and documentation consistent

In the chapter 'analogy with reader-writer locking', the sample
code uses spinlock_t in reader-writer case. Just correct it so
that we can read the document easily.

Signed-off-by: Yao Dongdong <yaodongdong@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agorcu: Consolidate dumping of ftrace buffer
Paul E. McKenney [Tue, 22 Mar 2016 02:46:04 +0000 (19:46 -0700)] 
rcu: Consolidate dumping of ftrace buffer

This commit consolidates a couple definitions and several calls for
single-shot ftrace-buffer dumping.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
8 years agoLinux 4.6-rc1
Linus Torvalds [Sat, 26 Mar 2016 23:03:24 +0000 (16:03 -0700)] 
Linux 4.6-rc1

8 years agoMerge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph...
Linus Torvalds [Sat, 26 Mar 2016 22:53:16 +0000 (15:53 -0700)] 
Merge branch 'for-linus' of git://git./linux/kernel/git/sage/ceph-client

Pull Ceph updates from Sage Weil:
 "There is quite a bit here, including some overdue refactoring and
  cleanup on the mon_client and osd_client code from Ilya, scattered
  writeback support for CephFS and a pile of bug fixes from Zheng, and a
  few random cleanups and fixes from others"

[ I already decided not to pull this because of it having been rebased
  recently, but ended up changing my mind after all.  Next time I'll
  really hold people to it.  Oh well.   - Linus ]

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (34 commits)
  libceph: use KMEM_CACHE macro
  ceph: use kmem_cache_zalloc
  rbd: use KMEM_CACHE macro
  ceph: use lookup request to revalidate dentry
  ceph: kill ceph_get_dentry_parent_inode()
  ceph: fix security xattr deadlock
  ceph: don't request vxattrs from MDS
  ceph: fix mounting same fs multiple times
  ceph: remove unnecessary NULL check
  ceph: avoid updating directory inode's i_size accidentally
  ceph: fix race during filling readdir cache
  libceph: use sizeof_footer() more
  ceph: kill ceph_empty_snapc
  ceph: fix a wrong comparison
  ceph: replace CURRENT_TIME by current_fs_time()
  ceph: scattered page writeback
  libceph: add helper that duplicates last extent operation
  libceph: enable large, variable-sized OSD requests
  libceph: osdc->req_mempool should be backed by a slab pool
  libceph: make r_request msg_size calculation clearer
  ...

8 years agoMerge tag 'ofs-pull-tag-1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap...
Linus Torvalds [Sat, 26 Mar 2016 19:59:04 +0000 (12:59 -0700)] 
Merge tag 'ofs-pull-tag-1' of git://git./linux/kernel/git/hubcap/linux

Pull orangefs filesystem from Mike Marshall.

This finally merges the long-pending orangefs filesystem, which has been
much cleaned up with input from Al Viro over the last six months.  From
the documentation file:

 "OrangeFS is an LGPL userspace scale-out parallel storage system.  It
  is ideal for large storage problems faced by HPC, BigData, Streaming
  Video, Genomics, Bioinformatics.

  Orangefs, originally called PVFS, was first developed in 1993 by Walt
  Ligon and Eric Blumer as a parallel file system for Parallel Virtual
  Machine (PVM) as part of a NASA grant to study the I/O patterns of
  parallel programs.

  Orangefs features include:

    - Distributes file data among multiple file servers
    - Supports simultaneous access by multiple clients
    - Stores file data and metadata on servers using local file system
      and access methods
    - Userspace implementation is easy to install and maintain
    - Direct MPI support
    - Stateless"

see Documentation/filesystems/orangefs.txt for more in-depth details.

* tag 'ofs-pull-tag-1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux: (174 commits)
  orangefs: fix orangefs_superblock locking
  orangefs: fix do_readv_writev() handling of error halfway through
  orangefs: have ->kill_sb() evict the VFS side of things first
  orangefs: sanitize ->llseek()
  orangefs-bufmap.h: trim unused junk
  orangefs: saner calling conventions for getting a slot
  orangefs_copy_{to,from}_bufmap(): don't pass bufmap pointer
  orangefs: get rid of readdir_handle_s
  ornagefs: ensure that truncate has an up to date inode size
  orangefs: move code which sets i_link to orangefs_inode_getattr
  orangefs: remove needless wrapper around GFP_KERNEL
  orangefs: remove wrapper around mutex_lock(&inode->i_mutex)
  orangefs: refactor inode type or link_target change detection
  orangefs: use new getattr for revalidate and remove old getattr
  orangefs: use new getattr in inode getattr and permission
  orangefs: use new orangefs_inode_getattr to get size in write and llseek
  orangefs: use new orangefs_inode_getattr to create new inodes
  orangefs: rename orangefs_inode_getattr to orangefs_inode_old_getattr
  orangefs: remove inode->i_lock wrapper
  orangefs: put register_chrdev immediately before register_filesystem
  ...

8 years agoMerge tag 'ntb-4.6' of git://github.com/jonmason/ntb
Linus Torvalds [Sat, 26 Mar 2016 18:37:42 +0000 (11:37 -0700)] 
Merge tag 'ntb-4.6' of git://github.com/jonmason/ntb

Pull NTB bug fixes from Jon Mason:
 "NTB bug fixes for tasklet from spinning forever, link errors,
  translation window setup, NULL ptr dereference, and ntb-perf errors.

  Also, a modification to the driver API that makes _addr functions
  optional"

* tag 'ntb-4.6' of git://github.com/jonmason/ntb:
  NTB: Remove _addr functions from ntb_hw_amd
  NTB: Make _addr functions optional in the API
  NTB: Fix incorrect clean up routine in ntb_perf
  NTB: Fix incorrect return check in ntb_perf
  ntb: fix possible NULL dereference
  ntb: add missing setup of translation window
  ntb: stop link work when we do not have memory
  ntb: stop tasklet from spinning forever during shutdown.
  ntb: perf test: fix address space confusion

8 years agoMerge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Linus Torvalds [Sat, 26 Mar 2016 18:31:01 +0000 (11:31 -0700)] 
Merge tag 'scsi-misc' of git://git./linux/kernel/git/jejb/scsi

Pull more SCSI updates from James Bottomley:
 "The only new stuff which missed the first pull request is an update to
  the UFS driver.

  The rest is an assortment of bug fixes and minor tweaks which appeared
  recently (some are fixes for recent code and some are stuff spotted
  recently by the checkers or the new gcc-6 compiler [most of Arnd's
  stuff])"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (32 commits)
  scsi_common: do not clobber fixed sense information
  scsi: ufs: select CONFIG_NLS
  scsi: fc: use get/put_unaligned64 for wwn access
  fnic: move printk()s outside of the critical code section.
  qla2xxx: avoid maybe_uninitialized warning
  megaraid_sas: add missing curly braces in ioctl handler
  lpfc: fix misleading indentation
  scsi_transport_sas: add 'scsi_target_id' sysfs attribute
  scsi_dh_alua: uninitialized variable in alua_check_vpd()
  scsi: ufs-qcom: add printouts of testbus debug registers
  scsi: ufs-qcom: enable/disable the device ref clock
  scsi: ufs-qcom: set PA_Local_TX_LCC_Enable before link startup
  scsi: ufs: add device quirk delay before putting UFS rails in LPM
  scsi: ufs: fix leakage during link off state
  scsi: ufs: tune UniPro parameters to optimize hibern8 exit time
  scsi: ufs: handle non spec compliant bkops behaviour by device
  scsi: ufs: add retry for query descriptors
  scsi: ufs: add error recovery after DL NAC error
  scsi: ufs: make error handling bit faster
  scsi: ufs: disable vccq if it's not needed by UFS device
  ...

8 years agof2fs/crypto: fix xts_tweak initialization
Linus Torvalds [Sat, 26 Mar 2016 17:13:05 +0000 (10:13 -0700)] 
f2fs/crypto: fix xts_tweak initialization

Commit 0b81d07790726 ("fs crypto: move per-file encryption from f2fs
tree to fs/crypto") moved the f2fs crypto files to fs/crypto/ and
renamed the symbol prefixes from "f2fs_" to "fscrypt_" (and from "F2FS_"
to just "FS" for preprocessor symbols).

Because of the symbol renaming, it's a bit hard to see it as a file
move: use

    git show -M30 0b81d07790726

to lower the rename detection to just 30% similarity and make git show
the files as renamed (the header file won't be shown as a rename even
then - since all it contains is symbol definitions, it looks almost
completely different).

Even with the renames showing as renames, the diffs are not all that
easy to read, since so much is just the renames.  But Eric Biggers
noticed that it's not just all renames: the initialization of the
xts_tweak had been broken too, using the inode number rather than the
page offset.

That's not right - it makes the xfs_tweak the same for all pages of each
inode.  It _might_ make sense to make the xfs_tweak contain both the
offset _and_ the inode number, but not just the inode number.

Reported-by: Eric Biggers <ebiggers3@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoNTB: Remove _addr functions from ntb_hw_amd
Allen Hubbe [Mon, 21 Mar 2016 08:53:14 +0000 (04:53 -0400)] 
NTB: Remove _addr functions from ntb_hw_amd

Kernel zero day testing warned about address space confusion.  A virtual
iomem address was used where a physical address is expected.  The
offending functions implement an optional part of the api, so they are
removed.  They can be added later, after testing.

Fixes: a1b3695820aa490e58915d720a1438069813008b
Signed-off-by: Allen Hubbe <Allen.Hubbe@emc.com>
Acked-by: Xiangliang Yu <Xiangliang.Yu@amd.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
8 years agoorangefs: fix orangefs_superblock locking
Al Viro [Fri, 25 Mar 2016 23:56:34 +0000 (19:56 -0400)] 
orangefs: fix orangefs_superblock locking

* switch orangefs_remount() to taking ORANGEFS_SB(sb) instead of sb
* remove from the list _before_ orangefs_unmount() - request_mutex
in the latter will make sure that nothing observed in the loop in
ORANGEFS_DEV_REMOUNT_ALL handling will get freed until the end
of loop
* on removal, keep the forward pointer and zero the back one.  That
way we can drop and regain the spinlock in the loop body (again,
ORANGEFS_DEV_REMOUNT_ALL one) and still be able to get to the
rest of the list.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs: fix do_readv_writev() handling of error halfway through
Al Viro [Wed, 17 Feb 2016 01:15:43 +0000 (20:15 -0500)] 
orangefs: fix do_readv_writev() handling of error halfway through

Error should only be returned if nothing had been read/written.
Otherwise we need to report a short read/write instead.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs: have ->kill_sb() evict the VFS side of things first
Al Viro [Wed, 17 Feb 2016 02:08:29 +0000 (21:08 -0500)] 
orangefs: have ->kill_sb() evict the VFS side of things first

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs: sanitize ->llseek()
Al Viro [Wed, 17 Feb 2016 01:25:19 +0000 (20:25 -0500)] 
orangefs: sanitize ->llseek()

a) open files can't have NULL inodes
b) it's SEEK_END, not ORANGEFS_SEEK_END; no need to get cute.
c) make_bad_inode() on lseek()?

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs-bufmap.h: trim unused junk
Al Viro [Wed, 17 Feb 2016 01:12:04 +0000 (20:12 -0500)] 
orangefs-bufmap.h: trim unused junk

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs: saner calling conventions for getting a slot
Al Viro [Wed, 17 Feb 2016 01:10:26 +0000 (20:10 -0500)] 
orangefs: saner calling conventions for getting a slot

just have it return the slot number or -E... - the caller checks
the sign anyway

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs_copy_{to,from}_bufmap(): don't pass bufmap pointer
Al Viro [Wed, 17 Feb 2016 01:06:19 +0000 (20:06 -0500)] 
orangefs_copy_{to,from}_bufmap(): don't pass bufmap pointer

it's always __orangefs_bufmap

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoorangefs: get rid of readdir_handle_s
Al Viro [Wed, 17 Feb 2016 00:54:13 +0000 (19:54 -0500)] 
orangefs: get rid of readdir_handle_s

no point, really - we couldn't keep those across the calls of
getdents(); it would be too easy to DoS, having all slots exhausted.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
8 years agoMerge branch 'akpm' (patches from Andrew)
Linus Torvalds [Fri, 25 Mar 2016 23:59:11 +0000 (16:59 -0700)] 
Merge branch 'akpm' (patches from Andrew)

Merge fourth patch-bomb from Andrew Morton:
 "A lot more stuff than expected, sorry.  A bunch of ocfs2 reviewing was
  finished off.

   - mhocko's oom-reaper out-of-memory-handler changes

   - ocfs2 fixes and features

   - KASAN feature work

   - various fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (42 commits)
  thp: fix typo in khugepaged_scan_pmd()
  MAINTAINERS: fill entries for KASAN
  mm/filemap: generic_file_read_iter(): check for zero reads unconditionally
  kasan: test fix: warn if the UAF could not be detected in kmalloc_uaf2
  mm, kasan: stackdepot implementation. Enable stackdepot for SLAB
  arch, ftrace: for KASAN put hard/soft IRQ entries into separate sections
  mm, kasan: add GFP flags to KASAN API
  mm, kasan: SLAB support
  kasan: modify kmalloc_large_oob_right(), add kmalloc_pagealloc_oob_right()
  include/linux/oom.h: remove undefined oom_kills_count()/note_oom_kill()
  mm/page_alloc: prevent merging between isolated and other pageblocks
  drivers/memstick/host/r592.c: avoid gcc-6 warning
  ocfs2: extend enough credits for freeing one truncate record while replaying truncate records
  ocfs2: extend transaction for ocfs2_remove_rightmost_path() and ocfs2_update_edge_lengths() before to avoid inconsistency between inode and et
  ocfs2/dlm: move lock to the tail of grant queue while doing in-place convert
  ocfs2: solve a problem of crossing the boundary in updating backups
  ocfs2: fix occurring deadlock by changing ocfs2_wq from global to local
  ocfs2/dlm: fix BUG in dlm_move_lockres_to_recovery_list
  ocfs2/dlm: fix race between convert and recovery
  ocfs2: fix a deadlock issue in ocfs2_dio_end_io_write()
  ...

8 years agoMerge tag 'pm+acpi-4.6-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael...
Linus Torvalds [Fri, 25 Mar 2016 23:55:37 +0000 (16:55 -0700)] 
Merge tag 'pm+acpi-4.6-rc1-3' of git://git./linux/kernel/git/rafael/linux-pm

Pull power management fixlet from Rafael Wysocki:
 "One of commits in my previous pull request changed the permissions of
  drivers/power/avs/rockchip-io-domain.c to executable by mistake"

* tag 'pm+acpi-4.6-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  Fix permissions of drivers/power/avs/rockchip-io-domain.c

8 years agoMerge tag 'please-pull-preadv2' of git://git.kernel.org/pub/scm/linux/kernel/git...
Linus Torvalds [Fri, 25 Mar 2016 23:48:45 +0000 (16:48 -0700)] 
Merge tag 'please-pull-preadv2' of git://git./linux/kernel/git/aegl/linux

Pull ia64 update from Tony Luck:
 "Wire up new system calls p{read,write}v2 for ia64"

* tag 'please-pull-preadv2' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux:
  [IA64] Enable preadv2 and pwritev2 syscalls for ia64

8 years agoMerge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Linus Torvalds [Fri, 25 Mar 2016 23:39:05 +0000 (16:39 -0700)] 
Merge branch 'for-linus' of git://git./linux/kernel/git/dtor/input

Pull more input updates from Dmitry Torokhov:
 "Second round of updates for the input subsystem.

  The BYD PS/2 protocol driver now uses absolute reporting mode and
  should behave more like other touchpads; Synaptics driver needed to
  extend one of its quirks to a newer firmware version, and a few USB
  drivers got tightened up checks for the contents of their descriptors"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: sur40 - fix DMA on stack
  Input: ati_remote2 - fix crashes on detecting device with invalid descriptor
  Input: synaptics - handle spurious release of trackstick buttons, again
  Input: synaptics-rmi4 - remove check of Non-NULL array
  Input: byd - enable absolute mode
  Input: ims-pcu - sanity check against missing interfaces
  Input: melfas_mip4 - add hw_version sysfs attribute

8 years agothp: fix typo in khugepaged_scan_pmd()
Kirill A. Shutemov [Fri, 25 Mar 2016 21:22:20 +0000 (14:22 -0700)] 
thp: fix typo in khugepaged_scan_pmd()

!PageLRU should lead to SCAN_PAGE_LRU, not SCAN_SCAN_ABORT result.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoMAINTAINERS: fill entries for KASAN
Andrey Ryabinin [Fri, 25 Mar 2016 21:22:17 +0000 (14:22 -0700)] 
MAINTAINERS: fill entries for KASAN

Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Alexander Potapenko <glider@google.com>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agomm/filemap: generic_file_read_iter(): check for zero reads unconditionally
Nicolai Stange [Fri, 25 Mar 2016 21:22:14 +0000 (14:22 -0700)] 
mm/filemap: generic_file_read_iter(): check for zero reads unconditionally

If
 - generic_file_read_iter() gets called with a zero read length,
 - the read offset is at a page boundary,
 - IOCB_DIRECT is not set
-  and the page in question hasn't made it into the page cache yet,
then do_generic_file_read() will trigger a readahead with a req_size hint
of zero.

Since roundup_pow_of_two(0) is undefined, UBSAN reports

  UBSAN: Undefined behaviour in include/linux/log2.h:63:13
  shift exponent 64 is too large for 64-bit type 'long unsigned int'
  CPU: 3 PID: 1017 Comm: sa1 Tainted: G L 4.5.0-next-20160318+ #14
  [...]
  Call Trace:
   [...]
   [<ffffffff813ef61a>] ondemand_readahead+0x3aa/0x3d0
   [<ffffffff813ef61a>] ? ondemand_readahead+0x3aa/0x3d0
   [<ffffffff813c73bd>] ? find_get_entry+0x2d/0x210
   [<ffffffff813ef9c3>] page_cache_sync_readahead+0x63/0xa0
   [<ffffffff813cc04d>] do_generic_file_read+0x80d/0xf90
   [<ffffffff813cc955>] generic_file_read_iter+0x185/0x420
   [...]
   [<ffffffff81510b06>] __vfs_read+0x256/0x3d0
   [...]

when get_init_ra_size() gets called from ondemand_readahead().

The net effect is that the initial readahead size is arch dependent for
requested read lengths of zero: for example, since

  1UL << (sizeof(unsigned long) * 8)

evaluates to 1 on x86 while its result is 0 on ARMv7, the initial readahead
size becomes 4 on the former and 0 on the latter.

What's more, whether or not the file access timestamp is updated for zero
length reads is decided differently for the two cases of IOCB_DIRECT
being set or cleared: in the first case, generic_file_read_iter()
explicitly skips updating that timestamp while in the latter case, it is
always updated through the call to do_generic_file_read().

According to POSIX, zero length reads "do not modify the last data access
timestamp" and thus, the IOCB_DIRECT behaviour is POSIXly correct.

Let generic_file_read_iter() unconditionally check the requested read
length at its entry and return immediately with success if it is zero.

Signed-off-by: Nicolai Stange <nicstange@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agokasan: test fix: warn if the UAF could not be detected in kmalloc_uaf2
Alexander Potapenko [Fri, 25 Mar 2016 21:22:11 +0000 (14:22 -0700)] 
kasan: test fix: warn if the UAF could not be detected in kmalloc_uaf2

Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agomm, kasan: stackdepot implementation. Enable stackdepot for SLAB
Alexander Potapenko [Fri, 25 Mar 2016 21:22:08 +0000 (14:22 -0700)] 
mm, kasan: stackdepot implementation. Enable stackdepot for SLAB

Implement the stack depot and provide CONFIG_STACKDEPOT.  Stack depot
will allow KASAN store allocation/deallocation stack traces for memory
chunks.  The stack traces are stored in a hash table and referenced by
handles which reside in the kasan_alloc_meta and kasan_free_meta
structures in the allocated memory chunks.

IRQ stack traces are cut below the IRQ entry point to avoid unnecessary
duplication.

Right now stackdepot support is only enabled in SLAB allocator.  Once
KASAN features in SLAB are on par with those in SLUB we can switch SLUB
to stackdepot as well, thus removing the dependency on SLUB stack
bookkeeping, which wastes a lot of memory.

This patch is based on the "mm: kasan: stack depots" patch originally
prepared by Dmitry Chernenkov.

Joonsoo has said that he plans to reuse the stackdepot code for the
mm/page_owner.c debugging facility.

[akpm@linux-foundation.org: s/depot_stack_handle/depot_stack_handle_t]
[aryabinin@virtuozzo.com: comment style fixes]
Signed-off-by: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoarch, ftrace: for KASAN put hard/soft IRQ entries into separate sections
Alexander Potapenko [Fri, 25 Mar 2016 21:22:05 +0000 (14:22 -0700)] 
arch, ftrace: for KASAN put hard/soft IRQ entries into separate sections

KASAN needs to know whether the allocation happens in an IRQ handler.
This lets us strip everything below the IRQ entry point to reduce the
number of unique stack traces needed to be stored.

Move the definition of __irq_entry to <linux/interrupt.h> so that the
users don't need to pull in <linux/ftrace.h>.  Also introduce the
__softirq_entry macro which is similar to __irq_entry, but puts the
corresponding functions to the .softirqentry.text section.

Signed-off-by: Alexander Potapenko <glider@google.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agomm, kasan: add GFP flags to KASAN API
Alexander Potapenko [Fri, 25 Mar 2016 21:22:02 +0000 (14:22 -0700)] 
mm, kasan: add GFP flags to KASAN API

Add GFP flags to KASAN hooks for future patches to use.

This patch is based on the "mm: kasan: unified support for SLUB and SLAB
allocators" patch originally prepared by Dmitry Chernenkov.

Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agomm, kasan: SLAB support
Alexander Potapenko [Fri, 25 Mar 2016 21:21:59 +0000 (14:21 -0700)] 
mm, kasan: SLAB support

Add KASAN hooks to SLAB allocator.

This patch is based on the "mm: kasan: unified support for SLUB and SLAB
allocators" patch originally prepared by Dmitry Chernenkov.

Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agokasan: modify kmalloc_large_oob_right(), add kmalloc_pagealloc_oob_right()
Alexander Potapenko [Fri, 25 Mar 2016 21:21:56 +0000 (14:21 -0700)] 
kasan: modify kmalloc_large_oob_right(), add kmalloc_pagealloc_oob_right()

This patchset implements SLAB support for KASAN

Unlike SLUB, SLAB doesn't store allocation/deallocation stacks for heap
objects, therefore we reimplement this feature in mm/kasan/stackdepot.c.
The intention is to ultimately switch SLUB to use this implementation as
well, which will save a lot of memory (right now SLUB bloats each object
by 256 bytes to store the allocation/deallocation stacks).

Also neither SLUB nor SLAB delay the reuse of freed memory chunks, which
is necessary for better detection of use-after-free errors.  We
introduce memory quarantine (mm/kasan/quarantine.c), which allows
delayed reuse of deallocated memory.

This patch (of 7):

Rename kmalloc_large_oob_right() to kmalloc_pagealloc_oob_right(), as
the test only checks the page allocator functionality.  Also reimplement
kmalloc_large_oob_right() so that the test allocates a large enough
chunk of memory that still does not trigger the page allocator fallback.

Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrey Konovalov <adech.fo@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Konstantin Serebryany <kcc@google.com>
Cc: Dmitry Chernenkov <dmitryc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoinclude/linux/oom.h: remove undefined oom_kills_count()/note_oom_kill()
Tetsuo Handa [Fri, 25 Mar 2016 21:21:53 +0000 (14:21 -0700)] 
include/linux/oom.h: remove undefined oom_kills_count()/note_oom_kill()

A leftover from commit c32b3cbe0d06 ("oom, PM: make OOM detection in the
freezer path raceless").

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agomm/page_alloc: prevent merging between isolated and other pageblocks
Vlastimil Babka [Fri, 25 Mar 2016 21:21:50 +0000 (14:21 -0700)] 
mm/page_alloc: prevent merging between isolated and other pageblocks

Hanjun Guo has reported that a CMA stress test causes broken accounting of
CMA and free pages:

> Before the test, I got:
> -bash-4.3# cat /proc/meminfo | grep Cma
> CmaTotal:         204800 kB
> CmaFree:          195044 kB
>
>
> After running the test:
> -bash-4.3# cat /proc/meminfo | grep Cma
> CmaTotal:         204800 kB
> CmaFree:         6602584 kB
>
> So the freed CMA memory is more than total..
>
> Also the the MemFree is more than mem total:
>
> -bash-4.3# cat /proc/meminfo
> MemTotal:       16342016 kB
> MemFree:        22367268 kB
> MemAvailable:   22370528 kB

Laura Abbott has confirmed the issue and suspected the freepage accounting
rewrite around 3.18/4.0 by Joonsoo Kim.  Joonsoo had a theory that this is
caused by unexpected merging between MIGRATE_ISOLATE and MIGRATE_CMA
pageblocks:

> CMA isolates MAX_ORDER aligned blocks, but, during the process,
> partialy isolated block exists. If MAX_ORDER is 11 and
> pageblock_order is 9, two pageblocks make up MAX_ORDER
> aligned block and I can think following scenario because pageblock
> (un)isolation would be done one by one.
>
> (each character means one pageblock. 'C', 'I' means MIGRATE_CMA,
> MIGRATE_ISOLATE, respectively.
>
> CC -> IC -> II (Isolation)
> II -> CI -> CC (Un-isolation)
>
> If some pages are freed at this intermediate state such as IC or CI,
> that page could be merged to the other page that is resident on
> different type of pageblock and it will cause wrong freepage count.

This was supposed to be prevented by CMA operating on MAX_ORDER blocks,
but since it doesn't hold the zone->lock between pageblocks, a race
window does exist.

It's also likely that unexpected merging can occur between
MIGRATE_ISOLATE and non-CMA pageblocks.  This should be prevented in
__free_one_page() since commit 3c605096d315 ("mm/page_alloc: restrict
max order of merging on isolated pageblock").  However, we only check
the migratetype of the pageblock where buddy merging has been initiated,
not the migratetype of the buddy pageblock (or group of pageblocks)
which can be MIGRATE_ISOLATE.

Joonsoo has suggested checking for buddy migratetype as part of
page_is_buddy(), but that would add extra checks in allocator hotpath
and bloat-o-meter has shown significant code bloat (the function is
inline).

This patch reduces the bloat at some expense of more complicated code.
The buddy-merging while-loop in __free_one_page() is initially bounded
to pageblock_border and without any migratetype checks.  The checks are
placed outside, bumping the max_order if merging is allowed, and
returning to the while-loop with a statement which can't be possibly
considered harmful.

This fixes the accounting bug and also removes the arguably weird state
in the original commit 3c605096d315 where buddies could be left
unmerged.

Fixes: 3c605096d315 ("mm/page_alloc: restrict max order of merging on isolated pageblock")
Link: https://lkml.org/lkml/2016/3/2/280
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Hanjun Guo <guohanjun@huawei.com>
Tested-by: Hanjun Guo <guohanjun@huawei.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Debugged-by: Laura Abbott <labbott@redhat.com>
Debugged-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> [3.18+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agodrivers/memstick/host/r592.c: avoid gcc-6 warning
Arnd Bergmann [Fri, 25 Mar 2016 21:21:47 +0000 (14:21 -0700)] 
drivers/memstick/host/r592.c: avoid gcc-6 warning

The r592 driver relies on behavior of the DMA mapping API that is
normally observed but not guaranteed by the API.  Instead it uses a
runtime check to fail transfers if the API ever behaves

When CONFIG_NEED_SG_DMA_LENGTH is not set, one of the checks turns into a
comparison of a variable with itself, which gcc-6.0 now warns about:

drivers/memstick/host/r592.c: In function 'r592_transfer_fifo_dma':
drivers/memstick/host/r592.c:302:31: error: self-comparison always evaluates to false [-Werror=tautological-compare]
    (sg_dma_len(&dev->req->sg) < dev->req->sg.length)) {
                               ^

The check itself is not a problem, so this patch just rephrases the
condition in a way that gcc does not consider an indication of a mistake.
We already know that dev->req->sg.length was initially R592_LFIFO_SIZE, so
we can compare it to that constant again.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Quentin Lambert <lambert.quentin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: extend enough credits for freeing one truncate record while replaying truncate...
Xue jiufei [Fri, 25 Mar 2016 21:21:44 +0000 (14:21 -0700)] 
ocfs2: extend enough credits for freeing one truncate record while replaying truncate records

Now function ocfs2_replay_truncate_records() first modifies tl_used,
then calls ocfs2_extend_trans() to extend transactions for gd and alloc
inode used for freeing clusters.  jbd2_journal_restart() may be called
and it may happen that tl_used in truncate log is decreased but the
clusters are not freed, which means these clusters are lost.  So we
should avoid extending transactions in these two operations.

Signed-off-by: joyce.xue <xuejiufei@huawei.com>
Reviewed-by: Mark Fasheh <mfasheh@suse.de>
Acked-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: extend transaction for ocfs2_remove_rightmost_path() and ocfs2_update_edge_len...
Xue jiufei [Fri, 25 Mar 2016 21:21:41 +0000 (14:21 -0700)] 
ocfs2: extend transaction for ocfs2_remove_rightmost_path() and ocfs2_update_edge_lengths() before to avoid inconsistency between inode and et

I found that jbd2_journal_restart() is called in some places without
keeping things consistently before.  However, jbd2_journal_restart() may
commit the handle's transaction and restart another one.  If the first
transaction is committed successfully while another not, it may cause
filesystem inconsistency or read only.  This is an effort to fix this
kind of problems.

This patch (of 3):

The following functions will be called while truncating an extent:
ocfs2_remove_btree_range
  -> ocfs2_start_trans
  -> ocfs2_remove_extent
     -> ocfs2_truncate_rec
       -> ocfs2_extend_rotate_transaction
         -> jbd2_journal_restart if jbd2_journal_extend fail
       -> ocfs2_rotate_tree_left
         -> ocfs2_remove_rightmost_path
             -> ocfs2_extend_rotate_transaction
               -> ocfs2_unlink_subtree
                -> ocfs2_update_edge_lengths
                  -> ocfs2_extend_trans
                    -> jbd2_journal_restart if jbd2_journal_extend fail
  -> ocfs2_et_update_clusters
  -> ocfs2_commit_trans

jbd2_journal_restart() may be called and it may happened that the buffers
dirtied in ocfs2_truncate_rec() are committed while buffers dirtied in
ocfs2_et_update_clusters() are not, the total clusters on extent tree and
i_clusters in ocfs2_dinode is inconsistency.  So the clusters got from
ocfs2_dinode is incorrect, and it also cause read-only problem when call
ocfs2_commit_truncate() with the error message: "Inode %llu has empty
extent block at %llu".

We should extend enough credits for function ocfs2_remove_rightmost_path
and ocfs2_update_edge_lengths to avoid this inconsistency.

Signed-off-by: joyce.xue <xuejiufei@huawei.com>
Acked-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2/dlm: move lock to the tail of grant queue while doing in-place convert
xuejiufei [Fri, 25 Mar 2016 21:21:38 +0000 (14:21 -0700)] 
ocfs2/dlm: move lock to the tail of grant queue while doing in-place convert

We have found a bug when two nodes doing umount one after another.

1) Node 1 migrate a lockres that has 3 locks in grant queue such as
   N2(PR)<->N3(NL)<->N4(PR) to N2.  After migration, lvb of the lock
   N3(NL) and N4(PR) are empty on node 2 because migration target do not
   copy lvb to these two lock.

2) Node 3 want to convert to PR, it can be granted in
   __dlmconvert_master(), and the order of these locks is unchanged.  The
   lvb of the lock N3(PR) on node 2 is copyed from lockres in function
   dlm_update_lvb() while the lvb of lock N4(PR) is still empty.

3) Node 2 want to leave domain, it will migrate this lockres to node 3.
   Then node 2 will trigger the BUG in dlm_prepare_lvb_for_migration()
   when adding the lock N4(PR) to mres with the following message because
   the lvb of mres is already copied from lock N3(PR), but the lvb of lock
   N4(PR) is empty.

"Mismatched lvb in lock cookie=%u:%llu, name=%.*s, node=%u"

[akpm@linux-foundation.org: tweak comment]
Signed-off-by: xuejiufei <xuejiufei@huawei.com>
Acked-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: solve a problem of crossing the boundary in updating backups
jiangyiwen [Fri, 25 Mar 2016 21:21:35 +0000 (14:21 -0700)] 
ocfs2: solve a problem of crossing the boundary in updating backups

In update_backups() there exists a problem of crossing the boundary as
follows:

we assume that lun will be resized to 1TB(cluster_size is 32kb), it will
include 0~33554431 cluster, in update_backups func, it will backup super
block in location of 1TB which is the 33554432th cluster, so the
phenomenon of crossing the boundary happens.

Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Xue jiufei <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: fix occurring deadlock by changing ocfs2_wq from global to local
jiangyiwen [Fri, 25 Mar 2016 21:21:32 +0000 (14:21 -0700)] 
ocfs2: fix occurring deadlock by changing ocfs2_wq from global to local

This patch fixes a deadlock, as follows:

  Node 1                Node 2                  Node 3
1)volume a and b are    only mount vol a        only mount vol b
  mounted

2)                      start to mount b        start to mount a

3)                      check hb of Node 3      check hb of Node 2
                        in vol a, qs_holds++    in vol b, qs_holds++

4) -------------------- all nodes' network down --------------------

5)                      progress of mount b     the same situation as
                        failed, and then call   Node 2
                        ocfs2_dismount_volume.
                        but the process is hung,
                        since there is a work
                        in ocfs2_wq cannot beo
                        completed. This work is
                        about vol a, because
                        ocfs2_wq is global wq.
                        BTW, this work which is
                        scheduled in ocfs2_wq is
                        ocfs2_orphan_scan_work,
                        and the context in this work
                        needs to take inode lock
                        of orphan_dir, because
                        lockres owner are Node 1 and
                        all nodes' nework has been down
                        at the same time, so it can't
                        get the inode lock.

6)                      Why can't this node be fenced
                        when network disconnected?
                        Because the process of
                        mount is hung what caused qs_holds
                        is not equal 0.

Because all works in the ocfs2_wq are relative to the super block.

The solution is to change the ocfs2_wq from global to local.  In other
words, move it into struct ocfs2_super.

Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Xue jiufei <xuejiufei@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Cc: Junxiao Bi <junxiao.bi@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2/dlm: fix BUG in dlm_move_lockres_to_recovery_list
Joseph Qi [Fri, 25 Mar 2016 21:21:29 +0000 (14:21 -0700)] 
ocfs2/dlm: fix BUG in dlm_move_lockres_to_recovery_list

When master handles convert request, it queues ast first and then
returns status.  This may happen that the ast is sent before the request
status because the above two messages are sent by two threads.  And
right after the ast is sent, if master down, it may trigger BUG in
dlm_move_lockres_to_recovery_list in the requested node because ast
handler moves it to grant list without clear lock->convert_pending.  So
remove BUG_ON statement and check if the ast is processed in
dlmconvert_remote.

Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reported-by: Yiwen Jiang <jiangyiwen@huawei.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Tariq Saeed <tariq.x.saeed@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2/dlm: fix race between convert and recovery
Joseph Qi [Fri, 25 Mar 2016 21:21:26 +0000 (14:21 -0700)] 
ocfs2/dlm: fix race between convert and recovery

There is a race window between dlmconvert_remote and
dlm_move_lockres_to_recovery_list, which will cause a lock with
OCFS2_LOCK_BUSY in grant list, thus system hangs.

dlmconvert_remote
{
        spin_lock(&res->spinlock);
        list_move_tail(&lock->list, &res->converting);
        lock->convert_pending = 1;
        spin_unlock(&res->spinlock);

        status = dlm_send_remote_convert_request();
        >>>>>> race window, master has queued ast and return DLM_NORMAL,
               and then down before sending ast.
               this node detects master down and calls
               dlm_move_lockres_to_recovery_list, which will revert the
               lock to grant list.
               Then OCFS2_LOCK_BUSY won't be cleared as new master won't
               send ast any more because it thinks already be authorized.

        spin_lock(&res->spinlock);
        lock->convert_pending = 0;
        if (status != DLM_NORMAL)
                dlm_revert_pending_convert(res, lock);
        spin_unlock(&res->spinlock);
}

In this case, check if res->state has DLM_LOCK_RES_RECOVERING bit set
(res is still in recovering) or res master changed (new master has
finished recovery), reset the status to DLM_RECOVERING, then it will
retry convert.

Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Reported-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Tariq Saeed <tariq.x.saeed@oracle.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: fix a deadlock issue in ocfs2_dio_end_io_write()
Ryan Ding [Fri, 25 Mar 2016 21:21:23 +0000 (14:21 -0700)] 
ocfs2: fix a deadlock issue in ocfs2_dio_end_io_write()

The code should call ocfs2_free_alloc_context() to free meta_ac &
data_ac before calling ocfs2_run_deallocs().  Because
ocfs2_run_deallocs() will acquire the system inode's i_mutex hold by
meta_ac.  So try to release the lock before ocfs2_run_deallocs().

Fixes: af1310367f41 ("ocfs2: fix sparse file & data ordering issue in direct io.")
Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Acked-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: fix disk file size and memory file size mismatch
Ryan Ding [Fri, 25 Mar 2016 21:21:20 +0000 (14:21 -0700)] 
ocfs2: fix disk file size and memory file size mismatch

When doing append direct write in an already allocated cluster, and fast
path in ocfs2_dio_get_block() is triggered, function
ocfs2_dio_end_io_write() will be skipped as there is no context
allocated.

As a result, the disk file size will not be changed as it should be.
The solution is to skip fast path when we are about to change file size.

Fixes: af1310367f41 ("ocfs2: fix sparse file & data ordering issue in direct io.")
Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Acked-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: take ip_alloc_sem in ocfs2_dio_get_block & ocfs2_dio_end_io_write
Ryan Ding [Fri, 25 Mar 2016 21:21:18 +0000 (14:21 -0700)] 
ocfs2: take ip_alloc_sem in ocfs2_dio_get_block & ocfs2_dio_end_io_write

Take ip_alloc_sem to prevent concurrent access to extent tree, which may
cause the extent tree in an unstable state.

Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: fix ip_unaligned_aio deadlock with dio work queue
Ryan Ding [Fri, 25 Mar 2016 21:21:15 +0000 (14:21 -0700)] 
ocfs2: fix ip_unaligned_aio deadlock with dio work queue

In the current implementation of unaligned aio+dio, lock order behave as
follow:

in user process context:
  -> call io_submit()
    -> get i_mutex
<== window1
      -> get ip_unaligned_aio
        -> submit direct io to block device
    -> release i_mutex
  -> io_submit() return

in dio work queue context(the work queue is created in __blockdev_direct_IO):
  -> release ip_unaligned_aio
<== window2
    -> get i_mutex
      -> clear unwritten flag & change i_size
    -> release i_mutex

There is a limitation to the thread number of dio work queue.  256 at
default.  If all 256 thread are in the above 'window2' stage, and there
is a user process in the 'window1' stage, the system will became
deadlock.  Since the user process hold i_mutex to wait ip_unaligned_aio
lock, while there is a direct bio hold ip_unaligned_aio mutex who is
waiting for a dio work queue thread to be schedule.  But all the dio
work queue thread is waiting for i_mutex lock in 'window2'.

This case only happened in a test which send a large number(more than
256) of aio at one io_submit() call.

My design is to remove ip_unaligned_aio lock.  Change it to a sync io
instead.  Just like ip_unaligned_aio lock, serialize the unaligned aio
dio.

[akpm@linux-foundation.org: remove OCFS2_IOCB_UNALIGNED_IO, per Junxiao Bi]
Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
8 years agoocfs2: code clean up for direct io
Ryan Ding [Fri, 25 Mar 2016 21:21:12 +0000 (14:21 -0700)] 
ocfs2: code clean up for direct io

Clean up ocfs2_file_write_iter & ocfs2_prepare_inode_for_write:
 * remove append dio check: it will be checked in ocfs2_direct_IO()
 * remove file hole check: file hole is supported for now
 * remove inline data check: it will be checked in ocfs2_direct_IO()
 * remove the full_coherence check when append dio: we will get the
   inode_lock in ocfs2_dio_get_block, there is no need to fall back to
   buffer io to ensure the coherence semantics.

Now the drop dio procedure is gone.  :)

[akpm@linux-foundation.org: remove unused label]
Signed-off-by: Ryan Ding <ryan.ding@oracle.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Cc: Mark Fasheh <mfasheh@suse.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This page took 0.05021 seconds and 5 git commands to generate.